llm-benchmarks
githubdrose.io

sambanova-turbo Provider Benchmarks


Measured over the last 30 days

Models Tracked
1
Avg Tokens / Second
29.45
Avg Time to First Token (ms)
2140.63
Last Updated
Sep 1, 2026

All sambanova-turbo models

1 tracked · fastest first
ModelAvg Toks/SecMinMaxAvg TTF (ms)
Llama 3.3 70B Instruct52.4034.7064.601160.00

Frequently Asked Questions

Which sambanova-turbo model is fastest?
Based on recent tests, Llama 3.3 70B Instruct shows the highest average throughput among tracked sambanova-turbo models.
How many recent measurements feed this dashboard?
This provider summary aggregates 88 individual prompts measured across 81 monitoring runs over the past month.